meta-harness
Developed by stanford-iris-lab
Meta-Harness is a framework developed by Stanford IRIS Lab for automated search and end-to-end optimization of task-specific model harnesses—the code surrounding a base model that manages storage, retrieval, and context. It automates the discovery of optimal scaffolding and memory systems using proposer agents (like Claude Code) to iteratively refine harness code, as demonstrated in text classification and Terminal-Bench 2.0 experiments.
- End-to-end model harness search and optimization
- Support for memory-system and scaffold evolution
- Integration with proposer agents for automated code iteration
- Streamlined onboarding flow for adapting to new domains
desktop